sfrontull commited on
Commit
a5aaac0
1 Parent(s): 8e48c63

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -0
README.md CHANGED
@@ -21,3 +21,33 @@ This model is licensed under the [CC BY-NC-SA 4.0 License](https://creativecommo
21
 
22
  ## Usage
23
  To use this model for translation, you need to use the prefixes `>>ita<<` for translating to Italian and `>>lld_Latn<<` for translating to Ladin (Val Badia).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
 
22
  ## Usage
23
  To use this model for translation, you need to use the prefixes `>>ita<<` for translating to Italian and `>>lld_Latn<<` for translating to Ladin (Val Badia).
24
+
25
+ ## Citation
26
+
27
+ If you use this model, please cite the following paper:
28
+
29
+ ```bibtex
30
+ @inproceedings{frontull-moser-2024-rule,
31
+ title = "Rule-Based, Neural and {LLM} Back-Translation: Comparative Insights from a Variant of {L}adin",
32
+ author = "Frontull, Samuel and
33
+ Moser, Georg",
34
+ editor = "Ojha, Atul Kr. and
35
+ Liu, Chao-hong and
36
+ Vylomova, Ekaterina and
37
+ Pirinen, Flammie and
38
+ Abbott, Jade and
39
+ Washington, Jonathan and
40
+ Oco, Nathaniel and
41
+ Malykh, Valentin and
42
+ Logacheva, Varvara and
43
+ Zhao, Xiaobing",
44
+ booktitle = "Proceedings of the The Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)",
45
+ month = aug,
46
+ year = "2024",
47
+ address = "Bangkok, Thailand",
48
+ publisher = "Association for Computational Linguistics",
49
+ url = "https://aclanthology.org/2024.loresmt-1.13",
50
+ pages = "128--138",
51
+ abstract = "This paper explores the impact of different back-translation approaches on machine translation for Ladin, specifically the Val Badia variant. Given the limited amount of parallel data available for this language (only 18k Ladin-Italian sentence pairs), we investigate the performance of a multilingual neural machine translation model fine-tuned for Ladin-Italian. In addition to the available authentic data, we synthesise further translations by using three different models: a fine-tuned neural model, a rule-based system developed specifically for this language pair, and a large language model. Our experiments show that all approaches achieve comparable translation quality in this low-resource scenario, yet round-trip translations highlight differences in model performance.",
52
+ }
53
+ ```